Automated Machine Learning Analysis of Patients With Chronic Skin Disease Using a Medical Smartphone App: Retrospective Study.

BACKGROUND: Rapid digitalization in health care has led to the adoption of digital technologies; however, limited trust in internet-based health decisions and the need for technical personnel hinder the use of smartphones and machine learning applications. To address this, automated machine learning (AutoML) is a promising tool that can empower health care professionals to enhance the effectiveness of mobile health apps. OBJECTIVE: We used AutoML to analyze data from clinical studies involving patients with chronic hand and/or foot eczema or psoriasis vulgaris who used a smartphone monitoring app. The analysis focused on itching, pain, Dermatology Life Quality Index (DLQI) development, and app use. METHODS: After extensive data set preparation, which consisted of combining 3 primary data sets by extracting common features and by computing new features, a new pseudonymized secondary data set with a total of 368 patients was created. Next, multiple machine learning classification models were built during AutoML processing, with the most accurate models ultimately selected for further data set analysis. RESULTS: Itching development for 6 months was accurately modeled using the light gradient boosted trees classifier model (log loss: 0.9302 for validation, 1.0193 for cross-validation, and 0.9167 for holdout). Pain development for 6 months was assessed using the random forest classifier model (log loss: 1.1799 for validation, 1.1561 for cross-validation, and 1.0976 for holdout). Then, the random forest classifier model (log loss: 1.3670 for validation, 1.4354 for cross-validation, and 1.3974 for holdout) was used again to estimate the DLQI development for 6 months. Finally, app use was analyzed using an elastic net blender model (area under the curve: 0.6567 for validation, 0.6207 for cross-validation, and 0.7232 for holdout). Influential feature correlations were identified, including BMI, age, disease activity, DLQI, and Hospital Anxiety and Depression Scale-Anxiety scores at follow-up. App use increased with BMI >35, was less common in patients aged >47 years and those aged 23 to 31 years, and was more common in those with higher disease activity. A Hospital Anxiety and Depression Scale-Anxiety score >8 had a slightly positive effect on app use. CONCLUSIONS: This study provides valuable insights into the relationship between data characteristics and targeted outcomes in patients with chronic eczema or psoriasis, highlighting the potential of smartphone and AutoML techniques in improving chronic disease management and patient care.

Impact of an eHealth Smartphone App on Quality of Life and Clinical Outcome of Patients With Hand and Foot Eczema: Prospective Randomized Controlled Intervention Study.

BACKGROUND: Chronic hand and foot eczema is a polyetiological dermatological condition. Patients experience pain, itching, and sleep disturbances and have a reduced quality of life. Skin care programs and patient education can improve the clinical outcome. eHealth devices offer a new opportunity to better inform and monitor patients. OBJECTIVE: This study aimed to systematically analyze the effect of a monitoring smartphone app combined with patient education on the quality of life and clinical outcome of patients with hand and foot eczema. METHODS: Patients in the intervention group received an educational program; attended study visits on weeks 0, 12, and 24; and had access to the study app. Patients in the control group attended the study visits only. The primary end point was a statistically significant reduction in Dermatology Life Quality Index, pruritus, and pain at weeks 12 and 24. The secondary end point was a statistically significant reduction in the modified Hand Eczema Severity Index (HECSI) score at weeks 12 and 24. This is an interim analysis at week 24 of the 60-week randomized controlled study. RESULTS: In total, 87 patients were included in the study and randomized to the intervention group (n=43, 49%) or control group (n=44, 51%). Of the 87 patients, 59 (68%) completed the study visit at week 24. There were no significant differences between the intervention and control groups regarding quality of life, pain, itch, activity, and clinical outcome at weeks 12 and 24. Subgroup analysis revealed that, compared with the control group, the intervention group with an app use frequency of fewer than once every 5 weeks had a significant improvement in the Dermatology Life Quality Index at weeks 12 (P=.001) and 24 (P=.05), in pain measured on a numeric rating scale at weeks 12 (P=.02) and 24 (P=.02), and in the HECSI score at week 12 (P=.02). In addition, the HECSI scores assessed on the basis of pictures taken by the patients of their hands and feet correlated strongly with the HECSI scores recorded by physicians during regular personal visits (r=0.898; P=.002) even when the quality of the images was not that good. CONCLUSIONS: An educational program combined with a monitoring app that connects patients with their treating dermatologists can improve quality of life if the app is not used too frequently. In addition, telemedical care can at least partially replace personal care in patients with hand and foot eczema because the analysis of the pictures taken by the patients correlates strongly with that of the in vivo images. A monitoring app such as the one presented in this study has the potential to improve patient care and should be implemented in daily practice. TRIAL REGISTRATION: Deutsches Register Klinischer Studien DRKS00020963; https://drks.de/search/de/trial/DRKS00020963.